description [ICLR 2026][Multimodal VLM][Missing Modality] MoRA utilizes a set of "modality-shared + modality-specific" low-rank parameters to enable vision and text encoders to maintain cross-modal ...
description [ICCV 2025][Object Detection][Visual Prompt] This paper proposes ModPrompt, an encoder-decoder-based visual prompting strategy that adapts vision-language object detectors (e.g., ...
Abstract: Partially Relevant Video Retrieval (PRVR) aims to retrieve videos that match a given textual query only partially. This task is inherently challenging due to the modality gap between text ...